JP7490905B1 - Job search support system, job search support method and program - Google Patents

Abstract

The present invention provides a job search support system that motivates job seekers to correct their registered information.
[Solution] According to one aspect of the present invention, there is provided a job search support system. The job search support system includes a processor. The processor is configured to execute the following steps: In the reception step, a selection by the job seeker of at least one candidate job offer from among job offers to which the job seeker can apply. In the correction suggestion step, corrections to the job seeker's registered information are suggested based on the candidate job offers and reference information received in the reception step. The reference information includes correlations between the candidate job offers and the corrections.
[Selected Figure] Figure 1

Description

The present invention relates to a job search support system, a job search support method, and a program.

As disclosed in Patent Document 1, a technology is known that allows job seekers to register user information (resumes) and search for job listings (job postings).

JP 2003-85437 A

In the job search support services described above, it is advisable for job seekers to update their own registered information in order to increase the chances of matching with employers.

In consideration of the above circumstances, the present invention provides a job search support system that motivates job seekers to correct their registered information.

According to one aspect of the present invention, a job search support system is provided. The job search support system includes a processor. The processor is configured to execute the following steps: In the reception step, a selection by the job seeker of at least one candidate job offer from among job offers to which the job seeker can apply is received. In the correction suggestion step, corrections to the job seeker's registered information are suggested based on the candidate job offers and reference information received in the reception step. The reference information includes a correlation between the candidate job offers and the corrections.

According to this aspect, by selecting jobs that interest a job seeker from among the jobs that can be applied for, the job seeker is suggested to revise his/her registered information according to the selected job (candidate job). This makes it possible to motivate the job seeker to revise his/her registered information to increase the chances of matching with an employer.

1 is a configuration diagram showing a job search support system 1. FIG. FIG. 2 is a block diagram showing the hardware configuration of the server device 10. FIG. 2 is a block diagram showing the hardware configuration of a recruiter terminal 20 and a job seeker terminal 30. 2 is a block diagram showing functions realized by the server device 10 (control unit 11), the recruiter terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31). FIG. FIG. 13 is a diagram showing an example of a recommended job offer display screen RD displayed on a job seeker terminal 30. FIG. 13 is a diagram showing an example of a job offer viewing screen JD displayed on a job seeker terminal 30. FIG. 13 is a diagram showing an example of a registration information editing screen ED displayed on a job seeker terminal 30. FIG. 2 is an activity diagram showing the flow of information processing (recommended job offers presentation processing) executed by job seeking support system 1. FIG. 2 is an activity diagram showing the flow of information processing (processing for proposing corrections) executed by job seeking support system 1.

The following describes embodiments of the present invention with reference to the drawings. The various features shown in the following embodiments can be combined with each other.

The program for realizing the software appearing in this embodiment may be provided as a non-transitory computer-readable recording medium, or may be provided so that it can be downloaded from an external server, or may be provided so that the program is started on an external computer and its functions are realized on a client terminal (so-called cloud computing).

In this embodiment, a "unit" may also include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In addition, this embodiment handles various types of information, which may be represented, for example, by physical values of signal values representing voltage and current, high and low signal values as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculations may be performed on a circuit in the broad sense.

In the broad sense, a circuit is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, and memory. In other words, it includes application specific integrated circuits (ASICs), programmable logic devices (e.g., simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)), etc.

1. Hardware Configuration This section describes the hardware configuration.

<Job search support system 1>
1 is a configuration diagram showing a job search support system 1. The job search support system 1 comprises a communication line 2, a server device 10, a plurality of recruiter terminals 20, and a plurality of job seeker terminals 30. The server device 10, the recruiter terminals 20, and the job seeker terminals 30 are configured to be able to communicate with each other via the communication line 2. The connection between the server device 10, the recruiter terminals 20, and the job seeker terminals 30 may be wired or wireless.

The job search support system 1 constitutes part of a recruitment and job search system used by multiple recruiters (first recruiter U1 and second recruiter U2) and multiple job seekers (first job seeker U3 and third job seeker U4). The job search support system 1 mainly manages job seeker registration information and job postings. In one embodiment, the job search support system 1 is made up of one or more devices or components. These components are described below.

<Server device 10>
2 is a block diagram showing a hardware configuration of the server device 10. The server device 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. The control unit 11, the storage unit 12, and the communication unit 13 are electrically connected to each other inside the server device 10 via the communication bus 14.

<Control unit 11>
The control unit 11 processes and controls the overall operation related to the server device 10. The control unit 11 is, for example, a central processing unit (CPU). The control unit 11 realizes various functions related to the server device 10 by reading out a predetermined program stored in the storage unit 12. That is, information processing by software stored in the storage unit 12 can be specifically realized by the control unit 11, which is an example of hardware, and executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and may be implemented to have multiple control units 11 for each function. Also, a combination of these may be used.

<Storage unit 12>
The storage unit 12 stores various information defined by the above description. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs and the like related to the server device 10 executed by the control unit 11, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the program calculations. The storage unit 12 stores various programs, variables, etc. related to the server device 10 executed by the control unit 11.

<Communication unit 13>
The communication unit 13 is preferably a wired communication means such as USB, IEEE 1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as 3G/LTE/5G, BLUETOOTH (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the server device 10 may communicate various information from the outside via the communication unit 13 and the network.

The server device 10 may be in an on-premise form or in a cloud form. As a server device 10 in a cloud form, the above-mentioned functions and processes may be provided in the form of, for example, SaaS (Software as a Service) or cloud computing.

<Employer terminal 20>
Fig. 3 is a block diagram showing the hardware configuration of the recruiter terminal 20 and the job seeker terminal 30. As shown in Fig. 3A, the recruiter terminal 20 comprises a control unit 21, a memory unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the memory unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected inside the recruiter terminal 20 via the communication bus 26. The explanation of the control unit 21, the memory unit 22, and the communication unit 23 is omitted here because it is the same as the explanation of each unit in the server device 10. Note that the recruiter terminal 20 may be a terminal operated by a human resources agency that communicates with job seekers on behalf of the recruiter.

<Input unit 24>
The input unit 24 accepts operation inputs made by the user. The operation inputs are transferred as command signals to the control unit 21 via the communication bus 26. The control unit 21 may execute predetermined control or calculations based on the transferred command signals as necessary. The input unit 24 may be included in the housing of the recruiter terminal 20, or may be attached externally. For example, the input unit 24 may be implemented as a touch panel integrated with the output unit 25. When the input unit 24 is implemented as a touch panel, the user can input tap operations, swipe operations, and the like to the input unit 24. As the input unit 24, a switch button, a mouse, a track pad, a QWERTY keyboard, and the like can be adopted instead of a touch panel.

<Output unit 25>
The output unit 25 displays a screen of a graphical user interface (GUI) that can be operated by the user. The output unit 25 may be included in the housing of the recruiter terminal 20, or may be attached externally. Specifically, the output unit 25 may be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, or a plasma display. It is preferable that these display devices are implemented by using different devices depending on the type of recruiter terminal 20.

<Job Seeker Terminal 30>
3B , the job seeker terminal 30 includes a control unit 31, a memory unit 32, a communication unit 33, an input unit 34, an output unit 35, and a communication bus 36. The control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 are electrically connected inside the job seeker terminal 30 via the communication bus 36. Descriptions of the control unit 31, the memory unit 32, the communication unit 33, the input unit 34, and the output unit 35 will be omitted as they are similar to the descriptions of the respective units in the recruiter terminal 20.

2. Functional Configuration In this section, the functional configuration of the present embodiment will be described. Information processing by the software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11 (a processor included in the job search support system 1).

Figure 4 is a block diagram showing the functions realized by the server device 10 (control unit 11), the employer terminal 20 (control unit 21), and the job seeker terminal 30 (control unit 31).

As shown in FIG. 4A, the server device 10 (control unit 11) includes a basic display control unit 111, a registration unit 112, a publication unit 113, a reception unit 114, a presentation unit 115, a correction suggestion unit 116, a registration information editing unit 117, and an artificial intelligence unit 120. As shown in FIG. 4B, the recruiter terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212. As shown in FIG. 4C, the job seeker terminal 30 (control unit 31) includes a display unit 311 and an operation reception unit 312.

<Basic display control unit 111>
The basic display control unit 111 is configured to display various information on the recruiter terminal 20 and the job seeker terminal 30. For example, the basic display control unit 111 displays a resume and curriculum vitae prepared by the job seeker, a job advertisement and scouting document prepared by the recruiter, etc. on the display unit 211 of the recruiter terminal 20 or the display unit 311 of the job seeker terminal 30.

Employers include organizations such as profit-making corporations (e.g., companies), non-profit organizations (e.g., cooperatives, foundations), and public organizations (e.g., local governments). Employers also include recruitment agencies that act as agents of organizations to mediate between job seekers and organizations. Recruitment agencies are also called headhunters or agents.

<Registration Unit 112>
The registration unit 112 is configured to register job seekers to use the service. Specifically, the registration unit 112 accepts input from the operation acceptance unit 312 of the job seeker terminal 30, and registers the job seeker's registration information (hereinafter, job seeker registration information) including the job seeker's resume, curriculum vitae, and other profile information. The job seeker registration information is registered in a job seeker database stored in the memory unit 12, for example.

A "resume" is a document that mainly describes a job seeker's profile, current situation, educational background, employment history, desired working conditions, etc., while a "career history", also known as a résumé, is a document in which a job seeker conveys to an employer his or her work history, experience, skills, qualifications, etc. related to his or her past work. In addition, the job seeker registration information may also include the job seeker's desired conditions (desired industry, desired job type, etc.).

The registration unit 112 determines whether new job seeker registration information being accepted for registration contains all pre-defined required fields (whether all required fields have been entered), and if the required fields are included, registers the job seeker registration information in the job seeker database. If any required fields are missing, the registration unit 112, for example, presents the required fields that have not been entered on the job seeker terminal 30.

<Publication Section 113>
The disclosure unit 113 discloses the job seeker registration information registered by the registration unit 112 to employers. Specifically, the disclosure unit 113 discloses the job seeker registration information registered by the registration unit 112 that has passed a predetermined screening to employers who are using the job search support system 1. In the screening, for example, a determination is made as to whether the contents and amount of information in the job seeker registration information meet predetermined standards. Job seeker registration information that does not pass the screening is not disclosed to employers, and the job seeker is required to correct it. In other words, the job seeker registration information is in a provisionally registered state until it is disclosed, and is registered as a permanent registration once it passes the screening, and disclosed to employers.

A job seeker whose job seeker registration information has been made public to an employer (full registration) becomes a target for job seeker searches by employers in the recruitment support service provided by job search support system 1, and is able to receive scouting documents from employers. In addition, a job seeker who has been fully registered can search for jobs in the recruitment support service provided by job search support system 1, and is able to apply for jobs.

<Reception Unit 114>
The reception unit 114 is configured to receive input from the job seeker terminal 30 of the registered job seeker. Specifically, the reception unit 114 receives the selection by the job seeker of at least one candidate job offer from among the job offers to which the job seeker can apply. The "candidate job offer" is, for example, a job offer selected by the job seeker as a job to be viewed (i.e., the job seeker has instructed the job seeker terminal 30 to display the contents of the job posting), a job offer selected by the job seeker as a job to which a candidate label (bookmark) is to be assigned (i.e., the job seeker has instructed the job seeker to assign a candidate label), etc. The job offer to which the candidate label is assigned is, for example, registered in a bookmark list prepared for each job seeker. By referring to the bookmark list, the job seeker can select a job offer to be viewed, applied for, or the like, from among the job offers to which the candidate label is assigned. In addition, the "job offer to which the job seeker can apply" is a job offer registered in the job search support system 1 for which the job seeker satisfies the recruitment requirements.

The reception unit 114 may accept the job seeker's selection of at least one candidate job offer from among the "recommended job offers" presented by the presentation unit 115 described below. For example, the reception unit 114 may accept the selection of a recommended job offer to be registered in the bookmark list from among the recommended job offers presented based on the first reference information described below immediately after the registration of the job seeker registration information.

A job posting, which is the content of a job offer, lists job information for multiple items such as the name of the advertised position, the job content and working conditions (annual salary, job type, industry, work location, working style, work environment, etc.), application qualifications (skills), the desired personality, selling points, etc. The job posting may also include items such as the job title, headline, and information about the employer (company size (sales, number of employees, etc.), industry, etc.).

<Presentation Unit 115>
The presentation unit 115 is configured to present at least one recommended job offer recommended to the job seeker from among job offers to which the job seeker can apply, based on the job seeker characteristic information and the reference information. The presentation unit 115 extracts recommended job offers from among job offers to which the job seeker can apply, for example, in a procedure described below, and displays the extracted recommended job offer on the job seeker terminal 30, for example, as a “recommended job offer.”

The job seeker characteristic information is at least one of the job seeker registration information and the job seeker's behavioral history regarding job offers. "Behavioral history regarding job offers" includes, for example, viewing a job offer, applying for a job offer, registering a job offer in a bookmark list, replying to a scouting document sent based on a job offer, passing a job offer screening (document screening, interview screening, etc.). The behavioral history is composed of information indicating the job offer that was the target or starting point of the behavior and the content of the behavior. The behavioral history is recorded for each job seeker (i.e. linked to the job seeker registration information) in, for example, a job seeker database. When extracting recommended job offers, the presentation unit 115 may refer to both the job seeker registration information and the behavioral history, or may refer to only one of the job seeker registration information and the behavioral history.

The reference information used by the presentation unit 115 when extracting recommended job offers is stored, for example, in the storage unit 12. The reference information includes first reference information and second reference information that are used differently depending on the time after the registration of the registration information. "Time after registration" refers to the time after the date or time when the job seeker registration information is registered (provisionally registered) by the registration unit 112. In addition, for example, the first reference information and the second reference information may be used differently depending on whether a predetermined number of days have passed since the date of registration until the present.

The presentation unit 115 determines whether the time after registration of the job seeker registration information for presenting recommended job offers is the time to use the first reference information. This makes it possible to present appropriate recommended job offers according to the time after registration of the job seeker registration information by setting in advance the time to use the first reference information. The time to use the first reference information may be, for example, a fixed period of time from provisional registration by the registration unit 112 (e.g., one week from provisional registration), or a period until a specified event occurs (e.g., publication by the publication unit 113).

Therefore, when the time after registration of the job seeker registration information for which the recommended job offer is presented is before the publication of the job seeker registration information, the presentation unit 115 may present the recommended job offer based on the job seeker characteristic information and the first reference information, and when the time is after the publication of the job seeker registration information, the presentation unit 115 may present the recommended job offer based on the job seeker characteristic information and the second reference information. This allows the presentation of recommended job offers based on the minimum information for job seeker registration information that has not yet been published and is not yet complete, for example, close to the minimum content required for registration, while presenting recommended job offers with improved accuracy based on more information for job seeker registration information that has been published and has been completed to a certain extent. Therefore, by introducing job offers registered in the job search support system 1 at a certain level to job seekers immediately after registration, the value of the recruitment support service provided by the job search support system 1 can be immediately presented and continuous use of the recruitment support service can be encouraged. This allows the presentation of recommended job offers to job seekers who are relatively motivated immediately after registration, leading to actions such as viewing job offers, applying for job offers, and registering job offers in a bookmark list. Furthermore, after registering, job seekers can be provided with higher quality job recommendations.

The presentation unit 115 presents recommended job offers based on the first reference information, for example, immediately after the job seeker registration information is registered (i.e., when provisional registration is completed). The presentation unit 115 also presents recommended job offers based on the second reference information, for example, when the job seeker user performs an action such as logging in, editing the job seeker registration information, or replying to a scout document after the job seeker registration information is made public.

The first reference information includes a first correlation between the job seeker characteristic information and the job offer (information included in a job posting, information associated with the job offer, etc.). The second reference information includes a second correlation between the job seeker characteristic information and the job offer that is different from the first correlation. In other words, the first reference information and the second reference information are different information from each other.

Specifically, the elements of the job seeker characteristic information included in the first correlation (i.e., the contents of the job seeker characteristic information referenced together with the first reference information when extracting recommended job offers) are different from the elements of the job seeker characteristic information included in the second correlation (i.e., the contents of the job seeker characteristic information referenced together with the second reference information when extracting recommended job offers). For example, the first correlation describes the job type (or industry) and annual income of the job seeker registration information, among the job seeker characteristic information, and the relationship between various job offers (conditions for determining that a job offer is a recommended job offer), and the second correlation describes the job type (or industry), annual income, and bookmark list of the job seeker registration information, among the job seeker characteristic information, and the relationship between various job offers (conditions for determining that a job offer is a recommended job offer). In other words, the second correlation may include a relationship between the bookmark list and job offers that is not included in the first correlation.

In this way, when registration information is used as the job seeker characteristic information, it is preferable that the number of items of the registration information referenced by the presentation unit 115 together with the second reference information is greater than the number of items of the registration information referenced by the presentation unit 115 together with the first reference information. This makes it possible to provide simple job recommendations using the first reference information to job seekers whose job seeker characteristic information contains a small number of items (whose contents are described), while providing more accurate job recommendations using the second reference information to job seekers whose job seeker characteristic information contains a large number of items.

<First reference information>
When the presenting unit 115 refers to the job seeker registration information as the job seeker characteristic information, the first reference information is prepared as, for example, information including extraction conditions for extracting recommended job offers from job offers to which the job seeker can apply (for example, a code in which the extraction conditions are described). Specifically, the first reference information may include, as the first correlation (extraction conditions), first similarity judgment information indicating a job offer or industry that is the same as or similar to the job offer or industry included in the job seeker registration information, and an annual income condition. When the first reference information is used according to the time after the registration of the job seeker registration information that presents the recommended job offer (i.e., when the time after the registration of the job seeker registration information that presents the recommended job offer is the time of use of the first reference information), the presenting unit 115 presents, as the recommended job offer, a job offer that includes a job offer or industry that is the same as or similar to the job offer or industry included in the job seeker registration information and that satisfies the annual income condition for the annual income included in the job seeker registration information. As a result, if job seeker registration information including at least the job type or industry and annual salary is registered, job offers that the user (job seeker) finds attractive in terms of annual salary can be presented as recommended job offers.

The "job type or industry in the job seeker registration information" referred to by the presentation unit 115 includes the job seeker's desired job type or industry in addition to the job seeker's current job type or industry. The similarity between the job type (current job type or desired job type) or industry (current industry or desired industry) in the job seeker registration information and the job type or industry in the job advertisement is determined based on the "first similarity judgment information" (information defining the similarity range of the job type or industry) included in the first reference information. The first similarity judgment information may define at least one similar keyword for a keyword indicating the job type or industry, or may define a similarity criterion for the feature amount obtained by vectorizing the keyword indicating the job type or industry. The similarity criterion for the feature amount is a threshold value for the difference (vector distance) of the feature amounts of two job types or industries, and for example, job types or industries in which the difference in the feature amount is less than the threshold value (or the cosine similarity is equal to or greater than the threshold value) are determined to be similar to each other.

The "annual income condition" included in the first reference information may be, for example, that the annual income of the job offer satisfies the desired annual income included in the job seeker registration information (is an annual income range that overlaps with the desired annual income), that the annual income of the job offer (e.g., the minimum annual income in the case of an annual income range) is higher than the job seeker's current annual income (annual income included in the job seeker registration information), etc. Job offers that satisfy such annual income conditions are determined to be recommended job offers by the presentation unit 115. In addition, a lower limit value may be set to the numerical value obtained by subtracting the job seeker's current annual income from the annual income of the job offer. In other words, the annual income condition may be set to an increase amount relative to the job seeker's current annual income.

When the presentation unit 115 refers to the job seeker registration information as the job seeker characteristic information, the first reference information may include, as the first correlation, second similarity judgment information indicating an attribute identical or similar to the attribute included in the job seeker registration information, or third similarity judgment information indicating the similarity of the behavioral history, and a judgment criterion for the behavioral history. When the first reference information is used according to the time after the registration of the job seeker registration information for which the recommended job offer is presented, the presentation unit 115 may present, as the recommended job offer, a job offer whose behavioral history of the reference job seeker satisfies the judgment criterion. The reference job seeker is another job seeker whose registration information has an attribute identical or similar to the attribute included in the job seeker registration information, or another job seeker whose behavioral history is similar to that of the job seeker. This makes it possible to present, to the user job seeker, a job offer that is of high interest to the reference job seeker who has an attribute or behavioral history similar to the user. The reference job seeker is extracted from the job seeker whose registration information is registered in the job seeker database of the job search support system 1.

Examples of "attributes included in the job seeker registration information" include items such as occupation, industry, skills, and qualifications. The similarity between attributes in the job seeker registration information and attributes in the registration information of other job seekers is determined based on "second similarity judgment information" (information defining the range of similarity of attributes) included in the first reference information. The second similarity judgment information may define at least one similar keyword for a keyword indicating an attribute, or may define a similarity criterion for features obtained by vectorizing a keyword indicating an attribute or a sentence. The similarity criterion for features is a threshold for the difference (vector distance) between the features of two attributes, and for example, attributes whose difference in features is less than the threshold (or whose cosine similarity is equal to or greater than the threshold) are determined to be similar to each other.

The presentation unit 115 may extract reference job seekers based on the similarity of attributes of a single item (e.g., only job type), or may extract reference job seekers based on the similarity of attributes of each of multiple items (e.g., job type and skill). In addition, the similarity of the behavioral histories between job seekers is determined based on "third similarity judgment information" (information that defines the range of similarity in behavioral histories) included in the first reference information.

When the first reference information including the second similarity judgment information or the third similarity judgment information is used, the behavioral history used to extract the reference job seekers and the recommended job offers includes at least one of viewing a job offer, applying for a job offer, registering a job offer in a bookmark list, and replying to a scout document sent based on a job offer. The third similarity judgment information defines, for example, a threshold for similarity judgment for the number of common job offers among the job offers that were the subject of these actions by two job seekers. In other words, two job seekers who have viewed a number of common job offers equal to or greater than the threshold are judged to have similar behavioral histories based on the third similarity judgment information. The third similarity judgment information may define a criterion for similarity judgment based on a combination of multiple types of behavioral histories (for example, a similarity judgment using the number of common job offers among the job offers applied for and the number of common job offers among the job offers replied to the scout document). As such a criterion, for example, a judgment formula that compares a value obtained by adding weights for the number of common job offers for each behavioral history with a threshold is used.

When the first reference information including the second similarity judgment information or the third similarity judgment information is used, the criterion for extracting recommended job offers is that the behavior score calculated based on the behavioral history of multiple reference job seekers exceeds a predetermined threshold. This makes it possible to extract recommended job offers according to the active behavior of the reference job seekers regarding job offers, and therefore makes it possible to present recommended job offers that are likely to lead to similar behavior for the user (job seeker) himself/herself.

Specifically, the presentation unit 115 calculates an action score for each job posting using at least one of the number of reference job seekers viewed, the number of reference job seekers who applied, the number of reference job seekers registered in a bookmark list, and the number of replies to the scout document. The action score is set to be higher the greater the number of times the job posting is the subject of the action history (i.e., the number of reference job seekers who were the subject of the action). When calculating the action score, the presentation unit 115 may weight the job posting according to the type of action history. For example, the presentation unit 115 may set a weighting coefficient for the number of times the action history is for application greater than the weighting coefficient for the number of times other action histories are performed, and may set the action score to, for example, the sum of values obtained by multiplying the number of times each action history is performed by the respective weighting coefficient. This allows job postings with a high application rate from reference job seekers to be presented preferentially as recommended job postings.

The behavior score may also be calculated based on behavioral transition rates such as the percentage of people who viewed a job posting and then applied to that job posting (the number of applications divided by the number of views), the percentage of people who applied to a job posting and then passed the screening process for documents, interviews, etc., or were hired (the number of people who passed the screening process or were hired divided by the number of applications). The behavior score may also be calculated based on behavioral transition rates such as the percentage of people who received a scouting document from a recruiter and then applied to that job posting (the number of people who applied to the job posting based on the scouting document and then passed the screening process for documents, interviews, etc., or were hired (the number of people who passed the screening process or were hired divided by the number of people who sent the scouting message). In other words, the behavior score may be set to be higher as these behavioral transition rates are higher.

The first reference information may be a first recommended job offer determination model that has been trained to be capable of inputting job seeker characteristic information and outputting recommended job offers. In this case, when the first reference information is used depending on the time after registration of the job seeker registration information for which recommended job offers are presented, the presentation unit 115 inputs the job seeker characteristic information into the first recommended job offer determination model of the artificial intelligence unit 120 and causes the first recommended job offer determination model to output recommended job offers. This makes it possible to present recommended job offers based on a large number of job seeker characteristic information or information equivalent thereto.

The first recommended job vacancy judgment model is a learning model trained using data on job seeker characteristic information for learning (registration information and/or behavioral history of the learning target job seeker) and data on job vacancies included in the behavioral history of the learning target job seeker (for example, job vacancies applied for by the learning target job seeker, job vacancies for which the learning target job seeker has received a scouting document, job vacancies for which the learning target job seeker has passed screening (document screening or interview screening), job vacancies for which the learning target job seeker has been hired, etc.) as training data. Candidates for the learning target job seeker include all job seekers whose registration information is registered in the job seeker database. In this case, the parameters of the first recommended job vacancy judgment model calculated or tuned by the learning correspond to the first correlation. In particular, the first recommended job vacancy judgment model may be a learning model trained using data on the registration information of the learning target job seeker and data on job vacancies applied for by the learning target job seeker, job vacancies for which the learning target job seeker has passed screening, or job vacancies for which the learning target job seeker has been hired as training data.

When the registration information is used as the job seeker characteristic information, the first recommended job offer judgment model may be trained so as to be able to judge recommended job offers based on the job type or industry and annual income included in the registration information. In this case, the presentation unit 115 inputs the job seeker registration information to the first recommended job offer judgment model and causes the first recommended job offer judgment model to output recommended job offers. As a result, if the job seeker registration information including at least the job type or industry and annual income is registered, it is possible to cause the first recommended job offer judgment model to extract job offers that the user (job seeker) finds attractive in terms of annual income.

The first recommended job offer determination model may be a learning model that has learned the relationship (degree of association) between the registration information and behavioral history of multiple learning target job seekers. In this case, when the first reference information is used depending on the time after registration of the job seeker registration information for which recommended job offers are presented, the presentation unit 115 inputs job seeker characteristic information to the first recommended job offer determination model and causes the first recommended job offer determination model to output recommended job offers based on job offer information included in the learned behavioral history. As a result, job offers included in the behavioral history of other job seekers whose registration information and behavioral history are similar to that of the user job seeker are extracted as recommended job offers. Therefore, recommended job offers that are of high interest to job seekers similar to the user job seeker can be presented.

The behavioral history used to input or learn the first recommended job determination model includes at least one of viewing a job, applying for a job, registering a job in a bookmark list, replying to a scout document sent based on a job, and passing the screening process for a job. This allows recommended jobs to be extracted based on the active behavior of job seekers other than the user regarding job offers, or the screening results, so that recommended jobs that are likely to interest the job seeker who is the user, or recommended jobs with a high probability of being hired, can be presented.

The relevance between registered information and behavioral history is an index showing the likelihood that a job seeker who has the registered information will take an action included in the behavioral history (e.g., viewing a job posting, applying for a job posting, adding the job posting to a bookmark list, replying to a scouting message, passing the screening process by an employer, etc.). In other words, the higher the relevance, the more likely a job seeker who has the registered information will take an action such as viewing or applying for a job posting included in the behavioral history.

In the first recommended job determination model that has learned the relevance between registered information and behavioral history, when job seeker registration information is input as job seeker characteristic information, for example, job offers that are included in related behavioral history among the learned behavioral history and have a certain degree of relevance with the input job seeker registration information or job offers that are included in multiple related behavioral histories at a certain frequency or more are output as recommended job offers.

In addition, in the first recommended job offer determination model, when a behavioral history is input as job seeker characteristic information, for example, a job offer included in a similar behavioral history similar to the input behavioral history among the learned behavioral history, or a job offer that is included more frequently than a certain frequency in multiple similar behavioral histories, is output as a recommended job offer. The similarity of the behavioral histories is determined, for example, based on the number of common job offers among the job offers that are the subject of each of the two behavioral histories being compared (for example, whether the number of common job offers is more than a certain frequency).

The first recommended job offer determination model may be a learning model trained to be able to determine recommended job offers based on the behavioral history of a reference job seeker regarding job offers. The reference job seeker here is another job seeker with registered information having attributes that are the same as or similar to the attributes included in the job seeker registration information, or another job seeker with a behavioral history similar to that of the job seeker.

The first recommended job offer determination model may be a generative AI including a large-scale language model. In this case, the presentation unit 115 inputs the job seeker characteristic information, inputs a prompt including an instruction to output recommended job offers to the first recommended job offer determination model, and causes the first recommended job offer determination model to output the recommended job offers. Furthermore, in addition to the instruction to output the recommended job offers and the job seeker characteristic information, the presentation unit 115 may input a prompt into the first recommended job offer determination model in which, for example, one or more samples of job seeker characteristic information and one or more corresponding samples of recommended job offers are inserted as input and output samples.

When the first reference information is used depending on the time after registration of the job seeker registration information for which recommended job offers are presented and the job seeker registration information is used as the job seeker characteristic information, the presentation unit 115 may calculate a job offer score for each job offer based on the job seeker registration information and the first reference information, and determine the recommended job offer depending on the level of the job offer score. This makes it possible to present recommended job offers in various forms based on the job offer score. For example, the presentation unit 115 presents, to the job seeker terminal 30, a job offer whose calculated job offer score is equal to or greater than a predetermined threshold as a recommended job offer. The presentation unit 115 may also present multiple recommended job offers in order of the job offer score. Furthermore, the presentation unit 115 may cause the job offer score (degree of recommendation) to be displayed on the job seeker terminal 30.

The job score may be calculated based on a match score calculated based on a comparison between the details included in the job seeker registration information and the details included in the job, and a behavior score calculated based on the behavioral history of reference job seekers with other registration information that has the same or similar attributes as those included in the job seeker registration information. This makes it possible to present recommended jobs taking into consideration whether the job is suitable for the user job seeker and the interest level of reference job seekers who are similar to the user job seeker.

The items included in the job seeker registration information and the job posting that are compared when calculating the match score are, for example, the current job type, desired job type, current industry, desired industry, skills, qualifications, current annual income, desired annual income, etc. In addition, the first reference information for calculating the job posting score defines the match score using a table, function, etc. according to the similarity between the items included in the job seeker registration information and the items included in the job posting (contents of the job posting). The similarity is defined, for example, by the distance between a first feature value obtained by vectorizing the words or sentences included in the job seeker registration information and a second feature value obtained by vectorizing the words or sentences included in the job posting. For example, cosine similarity is used as the similarity, and the closer the cosine similarity is to 1, the greater the similarity. In addition, the first reference information may define the match score according to the difference between the current annual income or desired annual income of the job seeker registration information and the annual income of the job posting (for example, the increase in the current annual income). In addition, the first reference information may include a match score calculation model that is trained to be able to output a match score by inputting the job seeker registration information and the job posting.

The behavioral score used to calculate the job offer score is the same as the behavioral score used in the "criteria for extracting recommended jobs." In other words, the behavioral score is set to be higher the greater the number of times the job offer has been the subject of the behavioral history (i.e., the number of reference job seekers whose behavior has been the subject). In addition, the presentation unit 115 may weight the behavioral score according to the type of behavioral history when calculating the behavioral score. Furthermore, the first reference information may include a behavioral score calculation model that has been trained to input job seeker registration information and output a behavioral score based on the behavioral history of the reference job seekers.

The job score is calculated, for example, by adding up the values obtained by multiplying the match score and the behavior score by a weighting coefficient.

The first reference information for calculating the job score may be a job score calculation model that has been trained to be able to input the job seeker registration information and the job for which the score is to be calculated and output the job score. In this case, the presentation unit 115 inputs the job seeker registration information and the target job into the job score calculation model, and causes the job score calculation model to output the job score for the target job.

The job score calculation model is a learning model that is trained using job seeker registration information and job data for learning and the corresponding job score as training data. The job score calculation model may be a generative AI including a large-scale language model. In this case, the presentation unit 115 inputs the job seeker registration information and job offer, inputs a prompt including an instruction to output the job score to the job score calculation model, and causes the job score calculation model to output the job score. In addition to the instruction to output the job score, the job seeker registration information, and the job offer, the presentation unit 115 may also input a prompt into the job score calculation model that includes, for example, one or more samples of job seeker registration information and job offer, and one or more corresponding job score samples, as input and output samples.

The first reference information may include both information including extraction conditions for extracting recommended job offers by referring to the job seeker registration information (e.g., code in which the extraction conditions are written) and a first recommended job offer judgment model. For example, the presentation unit 115 may present to the job seeker at least one first recommended job offer extracted using information including the extraction conditions and at least one second recommended job offer extracted using the first recommended job offer judgment model. The first reference information may also include both information for calculating a job offer score by referring to the job seeker registration information (e.g., definitions of match score and behavior score) and a job offer score calculation model. The presentation unit 115 may present to the job seeker at least one first recommended job offer extracted based on the first job offer score calculated using information for calculating the job offer score and at least one second recommended job offer extracted based on the second job offer score calculated using the job offer score calculation model.

This allows recommended jobs to be extracted using a combination of two different conditions or models (e.g., extraction conditions and the first recommended job determination model) as reference information, making it possible to stably present appropriate jobs that suit the job seeker. In particular, for job seekers with relatively little registered information, such as job seekers who have just registered, the first recommended job determination model, which is a learning model, may not be able to successfully extract appropriate recommended jobs. However, by using information including extraction conditions for extracting recommended jobs on a rule-based basis as the first reference information, it is possible to stably present appropriate recommended jobs to the job seeker.

Figure 5 is a diagram showing an example of a recommended job display screen RD displayed on the job seeker terminal 30. At least one recommended job information RJ is displayed on the recommended job display screen RD. The recommended job information RJ displays, for example, the job title JT, expected annual salary JI, job type JO, work location JL, organization name JC, industry JB, etc. of the recommended job. By selecting any recommended job information RJ on the job seeker terminal 30, the job seeker can view the job corresponding to the recommended job information RJ, register it in a bookmark list, etc.

The presentation unit 115 may present recommended job offers to a job seeker who is a user for whom a certain period of time has passed since the last time he or she used (logged in) the job search support system 1, based on the job seeker registration information and the first reference information. In other words, the presentation unit 115 may determine that the time to use the first reference information is a period after the job seeker's last login, during the period following the registration of the job seeker registration information for which recommended job offers are presented.

<Second Reference Information>
The second reference information is referenced when the time after registration of the job seeker registration information that presents recommended job offers is not the time to use the first reference information (i.e., the time to use the second reference information). As described above, the second reference information includes a second correlation between the job seeker characteristic information and the job offer, which is different from the first correlation included in the first reference information. In other words, the algorithm for determining recommended job offers using the second reference information is different from the algorithm for determining recommended job offers using the first reference information.

The second reference information, like the first reference information, may be information including extraction conditions for extracting recommended job offers by referring to job seeker registration information (e.g., code describing the extraction conditions), or may be a second recommended job offer determination model trained to be capable of inputting job seeker characteristic information (job seeker registration information or behavioral history) and outputting recommended job offers.

The second recommended job vacancy judgment model uses different data for learning from the first recommended job vacancy judgment model. For example, the second recommended job vacancy judgment model uses data of registered information (e.g., registered information before publication by the publication unit 113) in which the period after registration is the period when the first reference information is used, and the second recommended job vacancy judgment model uses data of registered information (e.g., registered information after publication by the publication unit 113) in which the period after registration is the period when the second reference information is used.

<Revision Proposal Unit 116>
The correction suggestion unit 116 is configured to suggest to the job seeker that he or she correct his or her job seeker registration information. Specifically, the correction suggestion unit 116 suggests corrections to the job seeker registration information based on the candidate job offers and the third reference information accepted by the acceptance unit 114. The "corrections" include adding words or sentences to the job seeker registration information, deleting words or sentences included in the job seeker registration information, and replacing words or sentences included in the job seeker registration information (e.g., correcting an expression or summarizing a sentence). For example, the correction suggestion unit 116 causes the job seeker terminal 30 to display, as corrections, words that are recommended to be included in the job seeker registration information as recommended keywords.

The third reference information includes a correlation between the candidate job offers and the correction items. The third reference information is stored, for example, in the memory unit 12. The third reference information may be a correction judgment model that has been trained so as to be able to input at least one candidate job offer and output correction items. In this case, the correction suggestion unit 116 inputs the content (job posting) of at least one candidate job offer into the correction judgment model of the artificial intelligence unit 120, and causes the correction judgment model to output the correction items.

The correction judgment model is a learning model that determines the corrections required to correct the job seeker registration information to make it suitable for the candidate job. The correction judgment model is a learning model that learns from the training job posting data and the job seeker registration information data suitable for it (for example, those who have received a scout based on the job posting or those whose job posting has been concluded) as training data. In this case, the parameters of the correction judgment model that are calculated or tuned by learning correspond to the correlation between the candidate job posting and the corrections required.

The correction judgment model may be a generative AI including a large-scale language model. In this case, the correction suggestion unit 116 inputs the job posting of the candidate job, inputs a prompt including an instruction to output corrections to the job seeker registration information to the correction judgment model, and outputs the corrections to the correction judgment model. In addition to the instruction to generate and output the corrections and the job posting of the candidate job, the correction suggestion unit 116 may also input, as input and output samples, a prompt into which, for example, samples of job postings of one or more candidate jobs and samples of one or more corresponding corrections are inserted, to the correction judgment model.

The correction suggestion unit 116 may extract recommended information from the registered information of the first reference job seeker and suggest adding the recommended information as a correction. The first reference job seeker is another job seeker who has a history of actions related to a candidate job offer. "Actions related to a candidate job offer" include actions from an employer to a job seeker, such as receiving a scout document based on the candidate job offer and passing an examination (document screening, interview screening, etc.) for the candidate job offer. As a result, corrections are suggested for a candidate job offer in which the user job seeker is interested, by referring to the registered information of other job seekers who have experienced actions such as receiving a scout document and passing an examination. Therefore, corrections that are easy for the user job seeker to receive in relation to the candidate job offer can be suggested.

Note that "actions related to a candidate job offer" also include "actions related to a similar job offer similar to the candidate job offer." A "similar job offer" is a job offer that a job seeker can apply for, whose similarity to the candidate job offer, determined based on the information in the job posting, is equal to or exceeds a predetermined threshold. The similarity between two job offers is calculated, for example, by comparing features such as vector data of words or sentences included in the job posting, or by determining the similarity using a learning model (large-scale language model). The revision suggestion unit 116 refers to the job seeker database and extracts a first reference job seeker who has a history of actions related to the candidate job offer or a similar job offer.

The first reference job seeker may have a history of receiving scout documents created based on candidate job offers or similar job offers to the candidate job offers. This allows the user (job seeker) to be suggested modifications to his/her job seeker registration information to make it easier for him/her to receive scout documents from recommended job offers.

The revision suggestion unit 116 may extract recommended information by comparing words or sentences contained in the registration information of the first reference job seeker with words or sentences contained in the registration information of multiple job seekers other than the first reference job seeker (i.e., job seekers who do not have a history of actions such as receiving scouting documents from candidate job offers) among the job seekers registered in the job seeker database.

A specific procedure for extracting recommended information is, for example, as follows. First, the correction suggestion unit 116 uses natural language processing to extract first elements, which are words or sentences included in the registered information of the first reference job seeker. Similarly, the correction suggestion unit 116 uses natural language processing to extract second elements, which are words or sentences included in the registered information of job seekers other than the first reference job seeker. Next, the correction suggestion unit 116 extracts, from the extracted first elements, words or sentences that have not been extracted as second elements, as recommended information.

The recommended information proposed as corrections by the correction suggestion unit 116 may be words or sentences extracted from the registered information of a plurality of first reference job seekers based on the frequency of occurrence of the words or sentences contained in the registered information. This makes it possible to suggest corrections to the user (job seeker) that can increase the expected occurrence of an action, such as receiving a scouting document, from the recommended job offer.

Specifically, the correction suggestion unit 116 calculates the frequency of occurrence of these sentence components on a word or sentence basis for the registered information of multiple first reference job seekers extracted from the job seeker database. The correction suggestion unit 116 extracts, as recommended information, words or sentences whose frequency of occurrence is equal to or greater than a predetermined threshold from the sentence components included in the registered information of multiple first reference job seekers.

In particular, the correction suggestion unit 116 may calculate the frequency of occurrence of sentence components extracted by comparing the registered information of the first reference job seeker with the registered information of multiple job seekers other than the first reference job seeker as described above, and extract recommended information based on the frequency of occurrence.

The correction suggestion unit 116 may determine the recommended information according to the magnitude of the occurrence score of the sentence component based on the first occurrence frequency in the registered information of the first reference job seeker and the second occurrence frequency in the registered information of job seekers other than the first reference job seeker. The correction suggestion unit 116 increases the occurrence score of the sentence component the higher the first occurrence frequency is, and increases the occurrence score of the sentence component the lower the second occurrence frequency is. The correction suggestion unit 116 may also weight the first occurrence frequency and the second occurrence frequency. For example, the correction suggestion unit 116 may determine the occurrence score of a certain word by subtracting a value corresponding to the second occurrence frequency (e.g., a value obtained by multiplying the second occurrence frequency by a weighting coefficient) from a value corresponding to the first occurrence frequency (e.g., a value obtained by multiplying the first occurrence frequency by a weighting coefficient), and determine a word whose occurrence score is equal to or greater than a threshold as the recommended information.

The recommended information may be a word or sentence indicating a skill, a word or sentence indicating a qualification, or a word or sentence contained in a job summary. This simplifies the content of the corrections, making it easier for the job seeker (user) to accept the proposed content. It also promotes an improvement in the expected occurrence of actions such as receiving a scouting document. Note that a "job summary" is a text that describes the job seeker's work history. For example, the job summary describes the department, role or job type, job content, results or achievements, etc. in chronological order.

The revision suggestion unit 116 may determine the importance of job items included in the candidate job, and may also suggest adding important items with high importance as revision items. The importance is a value that is set in advance for each job item in the candidate job, or is determined based on the frequency of occurrence of search keywords used in job seeker searches. This makes it possible to encourage the user (job seeker) to revise the registered information so that it includes words or sentences that the employer focuses on.

The "job details included in the candidate job offer" may be keywords (e.g., words representing individual skills) or keyword categories that encompass multiple keywords (e.g., "IT skills", "accounting skills", etc.). That is, the importance may be set for each individual keyword, or for each keyword category. When an importance is set for a keyword category, the same importance is set for all keywords included in one keyword category. For example, if the importance of "IT skills" is set to "1", a keyword included in the "IT skills" category (e.g., "app development") is determined to have an importance of "1".

In addition, "job details included in candidate job postings" include details that are written outside the job posting. That is, "job details" may be keywords written in the job posting itself, or important details words that are not written in the job posting but are stored in association with the job posting as information about the job. For example, even if a keyword related to the abilities that an employer requires of a job seeker, such as "communication skills," is not written in the job posting itself, it may be stored in the database in association with the job as an important (highly important) important details word in advance by the employer. The revision suggestion unit 116 presents the addition of such important details words as revisions to the job seeker registration information.

When the importance is determined based on the frequency of occurrence of the search keyword, the revision suggestion unit 116 determines the importance of the words included in the recommended job posting by referring to importance determination information, such as the frequency of occurrence of each word or a table in which the importance based on the frequency of occurrence is recorded. The importance determination information is stored, for example, in the storage unit 12. In this case, the importance is set to be higher as the frequency of occurrence is higher. The frequency of occurrence of each word included in the importance determination information is calculated, for example, based on the search history of all job seekers in the recruitment support service provided by the job search support system 1. This allows the user, the job seeker, to modify the job seeker registration information to make it more likely to be found in a job seeker search by a job seeker.

The revision suggestion unit 116, for example, determines that a job description (word or sentence) whose determined importance is equal to or greater than a predetermined threshold and that is not included in the current job seeker registration information is an important description, and suggests that it be added to the job seeker registration information.

The correction suggestion unit 116 may extract recommended information from important items based on the frequency of appearance in the registration information of the second reference job seeker, and may suggest adding the recommended information as a correction item. The second reference job seeker here is another job seeker to whom a scouting document created based on the job posting of a candidate job offer or a similar job offer similar to the candidate job offer has been sent, or another job seeker whose registration information has been viewed by the employer of the candidate job offer or a similar job offer. This makes it possible to encourage the job seeker who is the user to add information contained in the registration information of the second reference job seeker that is attracting a lot of attention from the candidate job offer or similar job offers to his or her own registration information.

Specifically, the revision suggestion unit 116 extracts, from among the job listings (words or sentences) determined to be important, those job listings whose frequency of appearance in the registration information of multiple second reference job seekers is equal to or exceeds a predetermined threshold, as recommended information. This allows the job seeker user to revise the job seeker registration information to make it easier for the employer to send scouting documents and easier for the employer to view the registration information.

The second reference job seeker may also be another job seeker whose registration information includes information that is highly similar to information included in the job seeker registration information. This makes it possible to encourage the user job seeker to add information included in the registration information of the second reference job seeker whose attributes are similar to those of the user job seeker to his or her own registration information.

The "similarity of the descriptions" here is defined as the difference between a first feature obtained by vectorizing the words or sentences included in the job seeker registration information and a second feature obtained by vectorizing the words or sentences included in the registration information of another job seeker, and the smaller the difference, the greater the similarity. For example, the revision suggestion unit 116 extracts, as the second reference job seeker, a job seeker whose registration information includes descriptions such that the difference between the first feature and the second feature is less than a threshold value.

The correction suggestion unit 116 may input the job posting of a candidate job into the recommended information extraction model, have the recommended information extraction model output recommended information, and suggest the addition of the recommended information as a correction. The recommended information extraction model is an example of the correction determination model described above, and is a learning model that takes a job posting as input and is trained to be able to extract job items of high importance contained in the job posting as recommended information. This makes it possible to suggest corrections based on examples of extraction of recommended information (important items) from a large number of job postings.

The recommended information extraction model is a learning model trained using training job posting data and data indicating job items with high importance in the job posting as training data. The recommended information extraction model may be a generative AI including a large-scale language model. In this case, the revision suggestion unit 116 inputs the job posting of the candidate job, inputs a prompt including an instruction to output recommended information to the recommended information extraction model, and causes the recommended information to be output to the recommended information extraction model. In addition to the instruction to extract and output recommended information and the job posting of the candidate job, the revision suggestion unit 116 may input a prompt into the recommended information extraction model in which, for example, samples of job postings of one or more candidate jobs and samples of one or more corresponding recommended information are inserted as input and output samples.

The correction suggestion unit 116 may suggest additions, deletions, or edits to the entered items as corrections depending on the amount of information contained in the job seeker registration information. For example, the correction suggestion unit 116 may suggest adding information to items in the job seeker registration information that have not been filled in, items where the amount of information filled in (number of characters) is less than a predetermined value (e.g., the average value of other job seekers), etc. Specifically, the correction suggestion unit 116 may determine the items that require addition in this way, extract the recommended information described above for the items that require addition, and suggest adding the recommended information.

For example, the correction suggestion unit 116 may also suggest deleting words or sentences, summarizing sentences, etc., for items in the job seeker registration information where the amount of writing (number of characters) is greater than a predetermined value (e.g., the average value of other job seekers). Specifically, the correction suggestion unit 116 may determine items that require a reduction in the amount of writing in this way, and then present the deletion content (words or sentences to be deleted), summary content (summary sentence and original sentence to be replaced with the summary sentence), etc., for the items that require reduction.

The correction suggestion unit 116 may suggest corrections based on the candidate job on the candidate job viewing screen and display the corrections together with the contents of the candidate job. This allows the job seeker user to check the corrections against the candidate job, which can motivate the job seeker to correct their registered information.

The correction suggestion unit 116 may display an object that accepts instructions to edit the job seeker registration information along with the corrections on the candidate job viewing screen. This allows the job seeker registration information to be edited immediately from the candidate job viewing screen, making it easier to guide the job seeker user to correct his or her own registration information. An example of an object that accepts instructions is a button that can be selected and input on the job seeker terminal 30.

When multiple candidate job openings are selected (for example, when multiple job openings are registered in the bookmark list), the revision suggestion unit 116 may extract additional recommended information from the registered information of multiple first reference job seekers associated with each of the multiple candidate job openings, including candidate job openings other than the candidate job openings displayed on the viewing screen. As described above, the first reference job seekers are other job seekers who have a history of actions related to each candidate job opening. Each candidate job opening is associated with multiple first reference job seekers.

The additional recommended information is extracted from the registered information of the first reference job seekers in the same manner as the recommended information described above. That is, the correction suggestion unit 116 sets the words or sentences extracted from the registered information as additional recommended information, for example, based on the frequency of occurrence of the words or sentences contained in the registered information of the first reference job seekers.

6 is a diagram showing an example of a job offer viewing screen JD displayed on the job seeker terminal 30. The job offer viewing screen JD displays correction items CM and a job posting JP. The job posting JP is the content of the candidate job offer selected by the job seeker to view. The correction items CM include corrections proposed to the registration information of the job seeker viewing the candidate job offer. In the example of FIG. 6, the addition of skills (an example of recommended information) to the job seeker registration information is displayed as the correction items CM. The correction items CM include an update button B11 that accepts an instruction to edit the job seeker registration information. When the update button B11 is operated and input, an editing screen for the job seeker registration information described later is displayed on the job seeker terminal 30. In this way, the necessary skills and the like are presented while the user, the job seeker, is viewing a job offer, so that a guide for enriching the job seeker registration information can be provided to the job seeker. In addition, the job seeker registration information can be corrected to be more likely to attract the attention of the employer of the job being viewed, to receive a scouting document, and to be hired.

The correction suggestion unit 116 may display an object that accepts an instruction to update the job seeker registration information along with the corrections on the candidate job viewing screen. Upon receiving an operation input of the object, the correction suggestion unit 116 overwrites and saves the job seeker registration information reflecting the corrections to the job seeker registration information in the job seeker database. In this case, the update of the job seeker registration information is completed without the editing screen described below being displayed on the job seeker terminal 30. This allows the user (job seeker) to appropriately update the job seeker registration information to match the job of interest, without the trouble of updating the job seeker registration information.

The correction suggestion unit 116 may suggest corrections to the job seeker registration information by using the recommended job offers presented (extracted) by the presentation unit 115 instead of the candidate job offers selected by the job seeker who is the user. In other words, the correction suggestion unit 116 may suggest corrections based on at least one recommended job offer and the third reference information.

<Registration Information Editing Department 117>
The registered information editing unit 117 is configured to accept edits to the job seeker registration information from the job seeker terminal 30 and update the job seeker registration information. Specifically, upon receiving an instruction to edit the job seeker registration information from the job seeker terminal 30, the registered information editing unit 117 displays at least a part of the job seeker registration information in a state in which the corrections have been reflected, and accepts edits to the job seeker registration information.

Specifically, the registration information editing unit 117 transitions the display on the job seeker terminal 30 from a viewing screen to an editing screen, and causes the job seeker terminal 30 to display the updated registration information on the editing screen. The updated registration information is registration information obtained by adding recommended information (words or sentences) contained in the corrections to the job seeker registration information before editing, deleting words or sentences contained in the job seeker registration information before editing, or making replacements, etc. The registration information editing unit 117 may highlight the corrections in the updated registration information (changes from the job seeker registration information before editing) by coloring them, etc.

The registration information editing unit 117 accepts further modifications to the updated registration information from the job seeker terminal 30. Furthermore, upon receiving an input of completion of the update from the job seeker terminal 30, the registration information editing unit 117 overwrites and saves the updated registration information in the job seeker database.

The registration information editing unit 117 may present additional recommended information extracted by the correction suggestion unit 116 from the registration information of the first reference job seeker related to multiple candidate job offers, along with the job seeker registration information (updated registration information) in a state in which the correction items have been reflected. This makes it possible to present the job seeker user with additional recommended information based on the first reference job seeker related to other candidate job offers, in addition to suggestions for correction items based on the job offer currently being viewed. This makes it possible to provide the job seeker user with a wide range of materials to correct his or her own registration information.

Figure 7 is a diagram showing an example of the registration information editing screen ED displayed on the job seeker terminal 30. The registration information editing screen ED includes a registration information display area RA, a save button B21, an add button B22, and an option display area OA.

The registration information display area RA is an area that displays the updated registration information. In the example of FIG. 7, the contents of the "Skills" item, which is part of the updated registration information, are displayed. Specifically, the skills included in the updated registration information are displayed in each skill display field SF. When a skill display field SF in which no skills are displayed is selected, the registration information editing unit 117 accepts additional input of a skill. Also, when the add button B22 is operated and input, a skill display field SF is added. Furthermore, the registration information editing unit 117 also accepts modification and deletion of skills that have already been input in each skill display field SF.

The option display area OA is an area that displays additional recommended information derived from sources other than the job offer being viewed. In the example of FIG. 7, candidate skills SO extracted as additional recommended information (extracted from the registration information of multiple first reference job seekers) are displayed as objects that can be selected and input. The registration information editing unit 117 accepts the selection of candidate skills SO from the job seeker terminal 30, and adds the selected candidate skills SO to the updated registration information (i.e., adds it to the registration information display area RA).

When the save button B21 is operated, the job seeker registration information is saved with the content displayed in the registration information display area RA. In other words, the item of the job seeker registration information displayed in the registration information display area RA ("Skills" in the example of FIG. 7) is updated to the content displayed in the registration information display area RA.

<Artificial Intelligence Department 120>
The artificial intelligence unit 120 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the server device 10 in each functional unit may be a common one, or may be prepared individually for each functional unit.

The artificial intelligence unit 120 may be an AI (Artificial Intelligence) equipped with a transformer including GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, and GPT-3), BERT (Bidirectional Encoder Representations from Transformers), BART (Bidirectional and Auto-regressive Transformer), etc., or a language model such as a recurrent neural network (RNN), and may include a generative AI.

The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 120 can apply the above algorithms as appropriate.

The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data consists of a pair of input data for learning and output data (correct answer data). In addition, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used for a wide range of tasks.

The artificial intelligence unit 120 may be a general-purpose natural language processing learning model such as a large-scale language model (LLM) that has learned a huge amount of data as the artificial intelligence. Such a general-purpose learning model includes a language model that can handle various tasks without fine tuning by one-shot learning, few-shot learning, etc. In addition, the general-purpose learning model may be configured to be capable of handling various tasks by zero-shot learning as well. The artificial intelligence used in each functional unit of the control unit 11 may be a separate learning model, or may be a common general-purpose learning model.

The learning models included in the artificial intelligence unit 120 (learning models used in each functional unit, such as the recommended job offer determination model and the correction determination model) can undergo additional learning as transfer learning or fine tuning. For example, each time new job seeker registration information and new job postings are registered, the artificial intelligence unit 120 may perform additional learning and fine tuning using these as new training data. This improves the accuracy of the information output from the learning model.

The learning model included in the artificial intelligence unit 120 may be a learning model (distilled model) obtained by knowledge distillation using the original learning model. In knowledge distillation, a trained model such as a large-scale language model is used as a teacher model, and the parameters of the student model are adjusted so that the output loss (Soft Target Loss) of the student model (distilled model) relative to the output (Soft Target) of the teacher model is small, thereby learning the student model, and the student model becomes a distilled model. In addition, the student model may be trained so that the output loss (Hard Target Loss) of the student model relative to the correct label (Hard Target) of the teacher data (combination of input data and output data of the learning model) is small. Compared to the original learning model (teacher model), the distilled model has a smaller number of parameters and a smaller processing load while having performance close to that of the learning model. Therefore, by using the distilled model, the cost of the job search support system 1 can be reduced.

For example, the recommended job determination model or the modified judgment model may be a distilled model trained using a combination of input data and output data in a large-scale language model as training data. Furthermore, when the job search support system 1 is introduced, a large-scale language model may be used as the recommended job determination model or the modified judgment model, and when training data from the large-scale language model is accumulated, the distilled model obtained by knowledge distillation using the training data may be used as the recommended job determination model or the modified judgment model.

<Display section>
The display unit 211 of the recruiter terminal 20 and the display unit 311 of the job seeker terminal 30 each display a screen indicated by the screen data transmitted from the server device 10 .

<Operation acquisition section>
The operation acquisition unit 212 of the recruiting party terminal 20 accepts operations by a user (recruiter) who uses the recruiting party terminal 20. The operation acceptance unit 312 of the job seeker terminal 30 accepts operations by a user (job seeker) who uses the job seeker terminal 30.

3. Information Processing Method This section describes an information processing method of the server device 10. This information processing method is executed by a computer, with each unit of the server device 10 acting as each step.

Specifically, this information processing method includes the information processing of the first embodiment (processing for presenting recommended jobs) and the information processing of the second embodiment (processing for proposing corrections).

The information processing of the first embodiment includes a registration step, a first presentation step, a publication step, and a second presentation step. In the registration step, job seeker registration information is registered. In the first presentation step, at least one recommended job offer recommended to the job seeker from among job offers to which the job seeker can apply is presented based on the job seeker characteristic information and the first reference information. In the publication step, the registered job seeker registration information is made public to the employer. In the second presentation step, at least one recommended job offer recommended to the job seeker from among job offers to which the job seeker can apply is presented based on the job seeker characteristic information and the second reference information.

Figure 8 is an activity diagram showing the flow of information processing (recommended job posting presentation processing) executed by the job search support system 1. Below, the information processing is explained along with each activity in this activity diagram.

The process of presenting recommended job offers begins with the job seeker registering his/her own registration information. The job seeker inputs the information required for registration into the job seeker terminal 30 (activity A101). The server device 10 accepts the job seeker registration information input from the job seeker terminal 30 and registers it in the job seeker database (activity A102). Next, the server device 10 extracts recommended job offers (initial recommended job offers) based on the job seeker registration information before disclosure and the first reference information (activity A103). Furthermore, the server device 10 outputs the extracted initial recommended job offers to the job seeker terminal 30 (activity A104). As a result, the initial recommended job offers are displayed (presented) on the job seeker terminal 30 (activity A105).

The server device 10 also discloses the job seeker registration information for which certain conditions are satisfied to the employer (activity A106). Next, the server device 10 extracts recommended job offers (medium-term recommended job offers) based on the disclosed job seeker registration information and the second reference information (activity A107). Furthermore, the server device 10 outputs the extracted medium-term recommended job offers to the job seeker terminal 30 (activity A108). As a result, the medium-term recommended job offers are displayed (presented) on the job seeker terminal 30 (activity A109).

The information processing of the second embodiment includes a reception step, a correction suggestion step, and a registered information editing step. In the reception step, the selection of at least one candidate job offer by the job seeker from among jobs to which the job seeker can apply is accepted. In the correction suggestion step, corrections to the job seeker's registered information are suggested based on the candidate job offers and third reference information accepted in the reception step. In the registered information editing step, in response to an instruction, at least a portion of the job seeker registered information in a state where the corrections have been reflected is displayed, and edits to the job seeker registered information are accepted.

Figure 9 is an activity diagram showing the flow of information processing (processing for proposing corrections) executed by the job search support system 1. Below, the information processing is explained along with each activity in this activity diagram.

The process of proposing corrections begins with the selection of candidate job offers by the job seeker whose job seeker registration information is registered. The job seeker selects at least one candidate job offer on the job seeker terminal 30 as a job offer to be viewed, registered in a bookmark list, etc. (activity A201). The server device 10 accepts the input of the candidate job offers from the job seeker terminal 30 and acquires information on the candidate job offers (activity A202). Next, the server device 10 extracts recommended information that is proposed to be added to the job seeker registration information based on the candidate job offers and the third reference information (activity A203). Furthermore, the server device 10 outputs to the job seeker terminal 30 the updated registration information in which the extracted recommended information has been added to the job seeker registration information (activity A204). As a result, the updated registration information is displayed (presented) on the job seeker terminal 30 (activity A205).

The job seeker, who is the user, edits the updated registration information displayed on the job seeker terminal 30 as necessary (activity A206). The server device 10 accepts the edits made to the updated registration information by the job seeker terminal 30 (activity A207). Furthermore, the server device 10 registers the edited updated registration information in the job seeker database as new job seeker registration information (activity A208).

4. Operation The operation of this embodiment can be summarized as follows. That is, when a job seeker selects a job offer that interests him/her from among the job offers that he/she can apply for, the job seeker is suggested to modify the registered information according to the selected job offer (candidate job offer). Therefore, the job seeker can be motivated to modify the registered information to increase the chances of matching with the employer.

The above describes an embodiment of the present invention, but the present invention is not limited to this and can be modified as appropriate without departing from the technical concept of the invention.

5. Others In the above embodiment, the server device 10 performs various storage and control, but multiple external devices may be used instead of the server device 10. That is, various information and programs may be distributed and stored in multiple external devices using block chain technology or the like. In particular, the artificial intelligence unit 120 may be an external configuration of the server device 10. In that case, the artificial intelligence unit 120, which is an external configuration, is configured to receive input from each functional unit of the server device 10 and return the instructed output to the server device 10.

The control unit 11 does not necessarily have to include the presentation unit 115. In other words, the job search support system 1 does not necessarily have to present recommended job offers.

The aspect of this embodiment is not limited to the job search support system 1, and may be an information processing method or a program. The job search support method includes each step executed by the job search support system 1. The program causes a computer to execute each step of the job search support system 1.

It may be provided in the following ways:

(1) A job search support system comprising a processor, the processor being configured to execute the following steps: in a reception step, a selection by a job seeker of at least one candidate job offer from among job offers to which the job seeker can apply; in a correction suggestion step, corrections to the job seeker's registered information are suggested based on the candidate job offers and reference information received in the reception step, wherein the reference information includes a correlation between the candidate job offers and the corrections.

(2) In the job search support system described in (1) above, in the correction suggestion step, recommended information is extracted from the registered information of a first reference job seeker, and the addition of the recommended information is suggested as the correction, and the first reference job seeker is another job seeker who has a history of actions related to the candidate job offer.

(3) In the job search support system described in (2) above, the first reference job seeker has a history of receiving scouting documents created based on the candidate job offer or a similar job offer similar to the candidate job offer.

(4) In the job search support system described in (2) or (3) above, the recommendation information is a word or sentence extracted from the registered information of the first reference job seekers based on the frequency of occurrence of the word or sentence contained in the registered information.

(5) In the job search support system described in (4) above, the recommendation information is a word or sentence indicating a skill, a word or sentence indicating a qualification, or a word or sentence contained in a job summary.

(6) In the job search support system described in (1) above, in the modification suggestion step, the importance of job items included in the candidate job offers in the candidate job offers is determined, and the addition of important items with high importance is proposed as the modification item, where the importance is set in advance for each job item in the candidate job offers, or is determined based on the frequency of occurrence of search keywords used in job seeker searches.

(7) In the job search support system described in (6) above, in the correction suggestion step, recommended information is extracted from the important items based on the frequency of appearance in the registration information of a second reference job seeker, and the addition of the recommended information is suggested as the correction item, and here, the second reference job seeker is another job seeker to whom a scouting document created based on a job posting of the candidate job offer or a similar job offer similar to the candidate job offer is sent, or another job seeker whose registration information has been viewed by the recruiter of the candidate job offer or the similar job offer.

(8) In the job search support system described in (6) above, in the correction suggestion step, recommended information is extracted from the important items based on the frequency of appearance in the registration information of a second reference job seeker, and the addition of the recommended information is suggested as the correction item, where the second reference job seeker is another job seeker whose registration information includes information that is highly similar to the information included in the registration information of the job seeker.

(9) In the job search support system described in (6) above, in the correction suggestion step, the job posting of the candidate job is input to a recommended information extraction model, the recommended information extraction model is caused to output recommended information, and the addition of the recommended information is proposed as the correction, and the recommended information extraction model is a learning model that is trained to receive the job posting as input and to be able to extract job items of high importance contained in the job posting as the recommended information.

(10) In the job search support system described in any one of (1) to (9) above, in the correction suggestion step, the corrections based on the candidate job offer are suggested on the viewing screen for the candidate job offer, and the corrections are displayed together with the contents of the candidate job offer.

(11) In the job search support system described in (10) above, in the correction suggestion step, an object that accepts instructions to edit the registered information of the job seeker is displayed on the viewing screen, and the processor is configured to further execute the following step, and in the registered information editing step, upon receiving the instructions, at least a portion of the registered information of the job seeker with the corrections reflected is displayed, and edits to the registered information are accepted.

(12) In the job search support system described in (11) above, in the correction suggestion step, recommended information is extracted from the registered information of a plurality of first reference job seekers related to each of the plurality of candidate job openings, where the first reference job seekers are other job seekers who have a history of actions related to the candidate job openings, and in the registered information editing step, the recommended information is presented together with the registered information of the job seekers in a state in which the corrections have been reflected.

(13) A job search support method comprising steps executed by a job search support system described in any one of (1) to (12) above.

(14) A program that causes a computer to execute each step of the job search support system described in any one of (1) to (12) above.
Of course, this is not the case.

Finally, various embodiments of the present disclosure have been described, but these are presented as examples and are not intended to limit the scope of the invention. The novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. The embodiments and modifications thereof are within the scope and spirit of the invention, and are included in the scope of the invention and its equivalents as set forth in the claims.

1 : Job search support system 2 : Communication line 10 : Server device 11 : Control unit 12 : Memory unit 13 : Communication unit 14 : Communication bus 20 : Recruiter terminal 21 : Control unit 22 : Memory unit 23 : Communication unit 24 : Input unit 25 : Output unit 26 : Communication bus 30 : Job seeker terminal 31 : Control unit 32 : Memory unit 33 : Communication unit 34 : Input unit 35 : Output unit 36 : Communication bus 111 : Basic display control unit 112 : Registration unit 113 : Publication unit 114 : Reception unit 115 : Presentation unit 116 : Correction suggestion unit 117 : Registration information editing unit 120 : Artificial intelligence unit 211 : Display unit 212 : Operation acquisition unit 311 : Display unit 312 : Operation reception unit

Claims (14)

A job search support system,
A processor is provided.
The processor is configured to perform the steps of:
In the receiving step, a selection of at least one candidate job offer by the job seeker is received from among job offers to which the job seeker can apply;
a correction suggestion step of suggesting corrections to the job seeker's registered information based on the candidate job offers and reference information received in the reception step, wherein the reference information includes a correlation between the candidate job offers and the corrections. The job search support system according to claim 1,
In the modification suggestion step, recommended information is extracted from the registered information of the first reference job seeker, and the addition of the recommended information is proposed as the modification item;
wherein the first reference job seeker is another job seeker who has a history of actions related to the candidate job offer. The job search support system according to claim 2,
A job search support system, wherein the first reference job seeker has a history of receiving scout documents created based on the candidate job offer or a similar job offer similar to the candidate job offer. The job search support system according to claim 2,
the recommendation information is a word or a sentence extracted from the registered information of the first reference job seekers based on the frequency of appearance of the word or sentence contained in the registered information. 5. The job search support system according to claim 4,
The recommendation information is a word or sentence indicating a skill, a word or sentence indicating a qualification, or a word or sentence contained in a job summary. The job search support system according to claim 1,
In the modification suggestion step, the importance of job items included in the candidate job offer is determined, and the addition of important items having high importance is proposed as the modification item;
Here, the importance level is set in advance for each job description in the candidate job offers, or is determined based on the frequency of appearance of search keywords used in a job seeker search. 7. The job search support system according to claim 6,
In the correction suggestion step, recommended information is extracted from the important items based on an appearance frequency in the registered information of a second reference job seeker, and the addition of the recommended information is suggested as the correction item;
Here, the second reference job seeker is another job seeker to whom a scouting document created based on a job posting for the candidate job offer or a similar job offer similar to the candidate job offer has been sent, or another job seeker whose registered information has been viewed by the employer of the candidate job offer or the similar job offer, in this job search support system. 7. The job search support system according to claim 6,
In the correction suggestion step, recommended information is extracted from the important items based on an appearance frequency in the registered information of a second reference job seeker, and the addition of the recommended information is suggested as the correction item;
Here, the second reference job seeker is another job seeker who has registration information including information that is highly similar to information included in the registration information of the job seeker. 7. The job search support system according to claim 6,
In the modification suggestion step, the job posting of the candidate job offer is input to a recommendation information extraction model, and the recommendation information extraction model is caused to output recommendation information, and addition of the recommendation information is proposed as the modification item;
Here, the recommended information extraction model is a learning model that is trained to take the job posting as input and extract important job items contained in the job posting as the recommended information, in this job search support system. The job search support system according to claim 1,
In the modification suggesting step, the job search support system proposes modifications based on the candidate job offers on the viewing screen for the candidate job offers, and displays the modifications together with contents of the candidate job offers. The job search support system according to claim 10,
In the correction suggestion step, an object for accepting an instruction to edit the registered information of the job seeker is displayed on the viewing screen,
The processor is further configured to perform the steps of:
In the registered information editing step, the job search support system receives the instruction, displays at least a part of the registered information of the job seeker in a state where the corrections are reflected, and accepts edits to the registered information. The job search support system according to claim 11,
In the modification suggestion step, recommendation information is extracted from registration information of a plurality of first reference job seekers associated with each of the plurality of candidate job offers, where the first reference job seekers are other job seekers who have a history of actions related to the candidate job offers;
In the registration information editing step, the job search support system presents the recommended information together with the registration information of the job seeker in a state in which the corrections have been reflected. A job search support method, comprising:
A job search support method comprising the steps executed by the job search support system according to any one of claims 1 to 12. A program,
A program causing a computer to execute each step of the job search support system according to any one of claims 1 to 12.

Images